Earticle

With the development of mobile edge computing, how to utilize the computing power of edge computing to effectively and efficiently offload data and to compute offloading is of great research value. This paper studies the computation offloading problem of multi-user and multi-server in mobile edge computing. Firstly, in order to minimize system energy consumption, the problem is modeled by considering the joint optimization of the offloading strategy and the wireless and computing resource allocation in a multi-user and multi-server scenario. Additionally, this paper explores the computation offloading scheme to optimize the overall cost. As the centralized optimization method is an NP problem, the game method is used to achieve effective computation offloading in a distributed manner. The decision problem of distributed computation offloading between the mobile equipment is modeled as a multi-user computation offloading game. There is a Nash equilibrium in this game, and it can be achieved by a limited number of iterations. Then, we propose a distributed computation offloading algorithm, which first calculates offloading weights, and then distributedly iterates by the time slot to update the computation offloading decision. Finally, the algorithm is verified by simulation experiments. Simulation results show that our proposed algorithm can achieve the balance by a limited number of iterations. At the same time, the algorithm outperforms several other advanced computation offloading algorithms in terms of the number of users and overall overheads for beneficial decision-making.

Task offloading in multi-access edge computing (MEC) systems is critical for managing computational tasks in dynamic urban environments. Existing strategies face challenges such as high communication overheads and regional performance deviations including centralized and distributed methods. Clustering approaches have been explored to address these issues, yet they often rely on physical proximity to form clusters, overlooking the variability in task rate distributions across edges. To overcome these limitations, this paper proposes a graph-driven inter-cluster resource distribution (GIRD) clustering scheme that clusters edge nodes based on task request distribution and computing resource status, ensuring similar resource utilization across clusters. Building on this, a proximal policy optimization (PPO)-enabled intra-cluster task offloading algorithm (PITO) is introduced to determine one execution server for task offloading?either an edge server within a cluster or a cloud server?using various network state information. This dynamic decision-making process optimizes a multi-objective function that includes task processing delay, consumed energy, success rate, and cloud cost. Simulation results demonstrate the proposed GIRD-PITO framework achieves superior task success rates, reduced delays, and improved regional performance fairness, making it a promising solution for large-scale MEC systems.

In this paper, end devices are considered here as agent, which makes its decisions on whether the network will offload the computation tasks to the edge devices or not. To tackle the resource allocation and task offloading, paper formulated the computation resource allocation problems as a sum cost delay of this framework. An optimal binary computational offloading decision is proposed and then reinforcement learning is introduced to solve the problem. Simulation results demonstrate the effectiveness of this reinforcement learning based scheme to minimize the offloading cost derived as computation cost and delay cost in industrial internet of things scenarios.

Beyond 6G services and applications demand high and efficient processing capacity due to the massive connectivity of users equipment (UEs). However, the high computational capability and energy consumption of UEs are limited, which becomes a main challenge to overcome. Multi-access edge computing (MEC) has recently been studied widely as it can potentially assist complex tasks executed at UEs. Furthermore, several techniques have been proposed to optimize task offloading among users. Thus, another challenge in MEC is emerging due to the fact that mobile users do not always have a line-of-sight (LoS) to the base station (BS) due to the blocking object. Therefore, it can affect users data rate and result in incremental energy consumption. This research introduces the concept of reconfigurable intelligence surfaces (RIS) to support multiple-input-single-output (MISO) base stations (BS) in both uplink (UL) and downlink (DL) using BCD algorithms. While previous studies concentrate on enhancing task offloading and neglecting inter-user interference, this study suggests an optimization approach for UL and DL data rates, as well as minimizing task offloading delays. The results indicate that optimizing task placement, phase shift, and precoding can reduce the duration of task offloading.

The mobile device has been widely used in many areas. Task offloading is always used to overcome the limitation of processing ability and energy-supply of the mobile devices in the mobile cloud environment. Most researches suppose we know the detail of task (number of instructions) of every sub-task. But most of time, to get the detail of a task is very difficult. This paper uses the grey number to express that uncertain information and propose method to evaluate the performance of offloading tasks. Simulations show that our method selects the solution with the lowest energy consumption.

As autonomous driving and connected car technology advance, various deep learning applications for autonomous vehicles and complex traffic situations are increasing. Autonomous vehicles must collect and process vast amounts of sensor data to support various deep learning applications, but vehicles have limited computing resources to perform complex deep learning operations. Therefore, edge computing is a promising solution to complement the limitations of autonomous vehicles. In this paper, we design edge computing for efficient task processing in an autonomous driving environment using a driving simulator. Also, we propose a task scheduling and offloading method which determines the target server to offload a task according to the characteristics of the task and the computing resources. The effectiveness of the proposed method is verified through experimental evaluation in an autonomous driving environment, supporting multiple deep learning services that we established by using a driving simulator.

최근 인공지능 기술 발전으로 인해 자동차 산업에서의 이를 활용한 차량의 모든 측면을 다루고 있다. 차량은 더 이상 운송 수단으로만 보이지 않고, 이동성과 연결성을 통해 운전자와 승객에게 다양한 서비스를 제공하는 중심 역할을 수행한다. 그러나 이러한 서비스 제공을 위해서는 컴퓨팅 자원이 필요하며, 이로 차량의 한정된 자원을 해결하기위해 클라우드 컴퓨팅의 중요성이 부각 되고 있다. 그러나 클라우드 컴퓨팅은 처리 속도와 네트워크 지연 문제로 인해 서비스 품질(QoS: Quality of Service)을 보장하기 어렵다는 한계가 있다. 따라서 차량 엣지 컴퓨팅 기술(VEC: Vehicle Edge Computing)과 주차된 차량 엣지 컴퓨팅(PVEC; Parked Vehicle Edge Computing) 아이디어가 제안되었다. 주차된 차량 엣지 컴퓨팅은 주차된 차량의 자원을 활용하여 엣지 서버에서 작업을 처리하는 기술로, 주차된 차량의 대기 시간에 무사용 중인 컴퓨팅 자원을 활용하여 서비스를 개선하고 수익을 창출할 수 있다. 본 논문에서는 연합 형성 게임, VCG 메커니즘, 샤플리 밸류와 같은 게임 이론 개념을 활용하여 주차된 차량 간의 협력을 촉진하고 태스크를 효율적으로 분배할 수 있는 기법을 제시한다. PVEC 플랫폼에서 주차된 차량의 자원을 효과적으로 활용하는 방법을 제안하고 이를 성능 평가와 비교를 통해 입증하였다. 이를 통해 주차된 차량의 온보드 자원을 활용하여 서비스 품질을 향상시킬 수 있는 새로운 접근법을 제시한다.

Recent advancements in artificial intelligence technology have led to its extensive integration in various aspects of the automotive industry. Vehicles are no longer perceived solely as means of transportation; they now play a central role in providing a multitude of services to drivers and passengers through enhanced mobility and connectivity. However, to deliver such services, substantial computing resources are required, highlighting the growing importance of cloud computing. Nevertheless, cloud computing faces challenges in ensuring Quality of Service (QoS) due to processing speed and network latency issues. In response to these challenges, the significance of Vehicle Edge Computing (VEC) and the concept of Parked Vehicle Edge Computing (PVEC) have been proposed. Parked Vehicle Edge Computing leverages the resources of parked vehicles to process tasks at the edge server. This technology harnesses the idle computing resources of parked vehicles during their downtime, thereby improving services and generating revenue. This paper introduces techniques that utilize game theory concepts such as coalition formation games, VCG mechanisms, and Shapley value to promote collaboration among parked vehicles and efficiently distribute tasks. The proposed methods effectively utilize the resources of parked vehicles in the PVEC platform, enhancing service quality and demonstrating their performance through evaluation and comparison. This suggests a novel approach to leveraging the onboard resources of parked vehicles to enhance service quality.

차세대 네트워크에서는 제한된 자원을 가진 수많은 장치가 실시간 응용 서비스를 위해 지연에 민감 하고 복잡한 작업을 수행해야 함에 따라 작업 오프로딩과 자원 할당이 점차 중요해지고 있다. 이는 복 잡한 결정 문제로 사전 지식 없이 최적 결정을 선택할 수 있는 강화 학습을 통해 해결할 수 있다. 본 연구는 이를 위한 연합 심층 강화 학습의 연구 동향을 정리하고, 자원 제약과 학습 구조를 중심으로 분석한 후 향후 연구 방향을 제시하고자 한다.

Mobile edge computing (MEC) plays a crucial role in improving the performance of resource-constrained mobile devices by offloading computation-intensive tasks to nearby edge servers. However, existing methods often neglect the critical consideration of future task requirements when making offloading decisions. In this paper, we propose an innovative approach that addresses this limitation. Our method leverages recurrent neural networks (RNNs) to predict task sizes for future time slots. Incorporating this predictive capability enables more informed offloading decisions that account for upcoming computational demands. We employ genetic algorithms (GAs) to fine-tune fitness functions for current and future time slots to optimize offloading decisions. Our objective is twofold: minimizing total processing time and reducing energy consumption. By considering future task requirements, our approach achieves more efficient resource utilization. We validate our method using a real-world dataset from Google-cluster. Experimental results demonstrate that our proposed approach outperforms baseline methods, highlighting its effectiveness in MEC systems.

5G의 도래와 스마트 디바이스의 급격한 증가는 멀티 액세스 엣지 컴퓨팅(MEC)의 중요성을 부각시켰다. 이런 흐름 속에서, 특히 계산 집약적이고 지연시간에 민감한 애플리케이션의 효과적인 처리가 큰 관심을 받고 있다. 본 논문에 서는 이러한 도전 과제를 해결하기 위해 확률적인 MEC 환경을 고려한 새로운 태스크 오프로딩 전략을 연구한다. 먼저 동적인 태스크 요청 빈도와 불안정한 무선 채널 상태를 감안하여 차량의 전력 소모와 지연시간을 최소화하는 방안을 제시한다. 그리고 심층 강화학습(DRL) 기반의 오프로딩 기법을 중심으로 연구를 진행하였고, 로컬 연산 및 오프로딩 전송 전력 사이의 최적의 균형을 찾기 위한 방법을 제안한다. Deep Deterministic Policy Gradient (DDPG)와 Deep Q-Network (DQN) 기법을 활용하여 차량의 전력 사용량과 큐잉 지연시간을 분석하였다. 이를 통해 차량 기반의 MEC 환경에서의 최적의 성능 향상 전략을 도출 및 검증하였다.

The rise of 5G and the proliferation of smart devices have underscored the significance of multi-access edge computing (MEC). Amidst this trend, interest in effectively processing computation-intensive and latency-sensitive applications has increased. This study investigated a novel task offloading strategy considering the probabilistic MEC environment to address these challenges. Initially, we considered the frequency of dynamic task requests and the unstable conditions of wireless channels to propose a method for minimizing vehicle power consumption and latency. Subsequently, our research delved into a deep reinforcement learning (DRL) based offloading technique, offering a way to achieve equilibrium between local computation and offloading transmission power. We analyzed the power consumption and queuing latency of vehicles using the deep deterministic policy gradient (DDPG) and deep Q-network (DQN) techniques. Finally, we derived and validated the optimal performance enhancement strategy in a vehicle based MEC environment.

최근 사물인터넷 시스템의 전력 절감을 위해 실시간 태스크를 클라우드 또는 엣지 서버로 오프로딩하는 기술이 활발히 연구되고 있다. 충분한 컴퓨팅 자원을 갖춘 클라우드 서버로의 오프로딩은 모바일 시스템의 컴퓨팅 부담을 크게 줄일 수 있으며, 안정된 네트워크 망을 통한 근거리 엣지 서버로의 오프로딩을 통해 실시간 태스크의 데드라인 조건을 더욱 세밀하게 충족할 수 있다. 본 논문에서는 모바일 실시간 시스템의 전력 절감을 위해 기존의 프로세서 동적 전압 조절 기술과 저전력메모리 기술에 엣지/클라우드 서버로의 태스크 오프로딩을 함께 적용한 최적화를 수행했을 때 클라 우드와 엣지 서버의 효율성을 비교 분석한다. 특히, 태스크 집합의 부하와 네트워크 상황, 원격 서버의 컴퓨팅 능력 차이 에 따라 클라우드와 엣지 서버로의 오프로딩이 어떠한 영향을 초래하는지 실험을 통해 비교 분석한다.

Recent research has been actively exploring the technology of offloading real-time tasks to cloud or edge servers to reduce power consumption in Internet of Things (IoT) systems. Offloading to cloud servers, which possess ample computing resources, can significantly reduce the computational burden on mobile systems. More recently, offloading to nearby edge servers via stable network connections has gained attention as a method to more effectively meet the deadline requirements of real-time tasks. This paper compares and analyzes the impact of cloud and edge servers when task offloading is combined with traditional dynamic voltage scaling (DVS) and low-power memory technologies to optimize power-saving in mobile real-time systems. Specifically, we experimentally compare the trade-offs between offloading to cloud versus edge servers, depending on task set load, network conditions, and the computing capabilities of remote servers.

In vehicular edge computing (VEC) networks, the rapid expansion of intelligent transportation and the corresponding enormous numbers of tasks bring stringent requirements on timely task offloading. However, many tasks typically appear within a short period rather than arriving simultaneously, which makes it difficult to realize effective and efficient resource scheduling. In addition, some key information about tasks could be learned due to the regular data collection and uploading processes of sensors, which may contribute to developing effective offloading strategies. Thus, in this paper, we propose a model that considers the deterministic demand of multiple tasks. It is possible to generate effective resource reservations or early preparation decisions in offloading strategies if some feature information of the deterministic demand can be obtained in advance. We formulate our scenario as a 0-1 programming problem to minimize the average delay of tasks and transform it into a convex form. Finally, we proposed an efficient optimal offloading algorithm that uses the interior point method. Simulation results demonstrate that the proposed algorithm has great advantages in optimizing offloading utility.

Edge computing deploys computing resources to the network edge to diminish task processing delays and power consumption. However, in traffic video surveillance systems, vehicular movement can lead to service interruptions. Moreover, the low credibility of the edge systems affects the success rate of edge offloading. To address these issues, we propose a secure task offloading scheme for traffic video surveillance. This scheme comprehensively evaluates trust values by integrating direct and indirect trust values, selecting nodes based on predefined trust thresholds, and achieving secure offloading and migration with short delays and energy consumption. To model the service migration problem, we adopted a Markov decision process-based approach and employed a Q-learning algorithm to determine the optimal solution, thereby establishing an effective migration path. Simulation results demonstrate that the proposed scheme yields higher comprehensive trust values and improved reliability. Furthermore, while ensuring seamless task migration, the migration success rate exceeded 90%, with the energy consumption reduced by more than 9.8%.

모바일 엣지 컴퓨팅(Mobile Edge Computing, MEC)은 높은 컴퓨팅 성능을 요구하는 작업을 모바일 장치에서 가까운 MEC 서버로 오프로딩함으로써 모바일 서비스에 높은 계산 요구량을 효율적으로 제공할 수 있는 기술로 부상하였다. 본 논문에서는 실행 대기 시간과 장치 에너지 소비를 줄이기 위해 여러 가지의 독립적 작업을 통해 MEC 시스템에 대한 작업 오프로드 일정 및 전송 에너지 할당을 최적화하는 기법을 제안한다. 시뮬레이션 결과로 MEC 시스템에서 사용 가능한 무선 및 계산 리소스가 상대적으로 균형 잡혀있는 경우 작업 오프로딩 일정이 더 중요하다는 것을 확인했다.

도로와 주변의 상황을 정확히 인지하는 객체탐지 기술은 자율주행 분야에 핵심적인 기술이다. 자율주행 분야에 객체탐지 기술은 추론 서비스의 정확도와 함께 실시간성도 요구된다. 고성능 머신이 아닌 자원제약 기기에서 정확도와 함께 실시간성을 위한 객체탐지 기술을 적용하기 위해서는 태스크 오프로딩 기술을 활용해야 한다. 본 논문에서는 자원 제약적 기기에서 자율주행의 실시간 객체탐지를 위한 태스크 오프로딩 적용과 관련하여 태스크 오프로딩의 성능 비교, 입력 이미지 해상도에 따른 성능 비교, 카메라 객체 해상도에 따른 성능 비교 등의 실험을 수행하고 결과를 분석하였다. 본 실험에서 낮은 해상도의 이미지는 태스크 오프로딩 구조의 적용을 통하여 성능 개선을 도출할 수 있었고, 이는 자율주행의 실시간 기준을 충족하였다. 높은 해상도의 이미지는 성능 개선은 있었으나 통신 시간의 증가에 따른 이유로 자율 주행의 실시간 기준을 충족하지 못하였다. 이러한 실험을 통해 자율주행에서의 객체인식은 사용하는 객체인식 모델과 함께 입력 이미지, 통신 환경 등의 다양한 조건이 영향을 미친다는 것을 확인할 수 있었다.

Object detection technology that accurately recognizes the road and surrounding conditions is a key technology in the field of autonomous driving. In the field of autonomous driving, object detection technology requires real-time performance as well as accuracy of inference services. Task offloading technology should be utilized to apply object detection technology for accuracy and real-time on resource-constrained devices rather than high-performance machines. In this paper, experiments such as performance comparison of task offloading, performance comparison according to input image resolution, and performance comparison according to camera object resolution were conducted and the results were analyzed in relation to the application of task offloading for real-time object detection of autonomous driving in resource-constrained devices. In this experiment, the low-resolution image could derive performance improvement through the application of the task offloading structure, which met the real-time requirements of autonomous driving. The high-resolution image did not meet the real-time requirements for autonomous driving due to the increase in communication time, although there was an improvement in performance. Through these experiments, it was confirmed that object recognition in autonomous driving affects various conditions such as input images and communication environments along with the object recognition model used.

5G 의 발전과 함께 차량과 IT 통신 기술을 융합한 어플리케이션들이 급증하면서 멀티 액세스 엣지 컴퓨팅(MEC)이 차세대 기술로 등장했다. 낮은 지연시간 안에 계산 집약적인 서비스들을 제공하기 위해 단독적인 MECS 서버(MECS)에서의 수행이 아닌 다수의 MECS 에서 동시에 연산을 수행할 수 있도록 태스크를 파티셔닝하는 기법이 주목받고 있다. 특히 차량이 다수의 MECS 로 태스크를 파티셔닝하여 오프로딩하는 기법과 하나의 MECS 로 오프로딩한 후 다른 MECS 들로 파티셔닝하여 마이그레이션하는 기법들이 연구되고 있다. 본 논문에서는 오프로딩과 마이그레이션을 이용한 파티셔닝 기법들을 서비스 지연시간과 차량의 에너지 소비량 측면에서 성능을 비교 분석을 하였다.